Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/doordash-oss/agentic-orchestrator/knowledge-readernpx skills add doordash-oss/agentic-orchestrator --skill knowledge-readergit clone --depth 1 https://github.com/doordash-oss/agentic-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/knowledge-reader)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/knowledge-reader"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/knowledge-reader.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.00662 |
| Opus 5 | $0.00013 | $0.00331 |
| Sonnet 5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
knowledge-reader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Reader
You have access to a pre-built Knowledge Base (KB) for the target repository. The KB index path and KB directory are listed in the Pre-flight section of your prompt — read the KB index first to see what categories are available.
The KB is a structured graph of markdown documents organized into categories. Each category has an index file and detailed leaf files. Start by reading the KB index, then use the KB directory path to read specific leaf files relevant to your task.
When to Read KB Leaf Files
Consult the KB before you:
| Situation | Read from these KB categories |
|---|---|
| Write or modify code | conventions/ — read the index, then leaf files for error handling, naming, code style |
| Write or modify tests | verification/ + conventions/ — test patterns, test infrastructure, testing conventions |
| Make architectural decisions | architecture/ — components, data flow, key abstractions |
| Use or extend APIs | api-surface/ — services, client libraries, config schemas |
| Add dependencies | dependencies/ — approved libraries, version constraints |
| Set up verification steps | verification/ — test suites, CI pipeline, verification order |
How to Navigate
- Read the KB index from the path listed in Pre-flight — it shows the category map, build commands, key architecture decisions, and important file paths
- Identify which categories are relevant to your current task using the table above
- Read the category's
index.mdfirst (e.g.,<KB Directory>/conventions/index.md) to discover the actual leaf filenames — these vary per repo - Read the relevant leaf files based on what the category index lists
- Only read what you need — typically 2-4 leaf files per task
Category Overview
| Category | What it covers |
|---|---|
architecture/ |
Component maps, data flow patterns, dependency injection modules, key abstractions, concurrency and persistence models |
conventions/ |
Error handling patterns (including error grading), naming conventions, testing patterns, code style, logging and context propagation |
api-surface/ |
gRPC services, CLI tools, client library API, configuration schemas, environment variables, Kafka event contracts |
dependencies/ |
Go library inventory, build tools (Task, Bazel, etc.), runtime services (Cassandra, CRDB, Kafka), version constraints |
verification/ |
Unit test patterns, integration test infrastructure, CI pipeline, linting rules, recommended verification order |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 49 lines · 26 tokens per session scan A a6746ae0a9e8
knowledge-reader is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (101 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 662 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…